SDD is good. It's a lot faster and cheaper to have an agent polish a spec, than refactor code. The implementation can then be verified against the spec artifact, and any drift can feed back into process improvements for future specs.
Not sure about your thesis. Still excited here, no dread. Linux works pretty well compared to the old days. Open source is stronger than ever.
> So lately, it's hard for anyone to know what their preferences really are.
Sway + keybinds for each workspace. Everything in it's place, every time, by pressing 3 keys. Foot terminal opens in sub-ms. MicroVM framework sandboxes workloads. The UX isn't that different from my older setups TBH, only the underlying tech. I'm open to trying new things, but I don't know how you can beat preconfigured workspace keybinds. Would love to hear any ideas though.
> and have no peers out there who are having fun
Having lots of fun lately! This LLM stuff is bananas! Not only can you ask your agent to do stuff in plain language, but it's non-deterministic so it's like RNG gambling except you can build a Rube Goldberg machine to increase your odds! Regardless, I'd still be having fun without LLMs. We have amazing languages and incredible hardware these days.
> the granularity of build it yourself systems is not great
NixOS takes some of the pain away. You can experiment easily and safely, and you have a single declarative source that captures everything. Admittedly this isn't mainstream, but you're talking about nvim frameworks so... yeah.
Anyway, chin up friend! There are some of us more stoked than ever on the current state of computing. There's so much exciting change happening it's amazing. I'm grumpy about lots of things, but computers are better than ever IMHO.
It gets hard to ignore the annoyance when the volume degrades the signal. At some point the people who wish to engage with the substance just nope out when they see a sea of banality, and that's all you're left with.
Either the complainers are whining about something that isn't there, you are failing to notice something that is there, or it's subjective. Only one out of those three options merits the confidence with which you're dismissing the people you disagree with.
But those people believe that sloppy wording is itself a strong signal that the speaker/writer is the one lacking in substance, and doesn't deserve the attention or trust of the listener.
That's not what my comment is about. The parent said you're free to ignore the complaints, and I pointed out that when the volume is high, that's hard to do.
We all know that clanker language is often ridiculously bad. Got it.
Maybe policing every word and sentence and lodging your complaint along with all the other similar complaints is the right move. The squeaky wheel gets the grease. But meanwhile we're degrading the overall discourse on the topic at hand.
I'm not saying which is right, I'm saying there's a cost to constantly expressing one's annoyance on a well-worn subject. If you click a thread about X to read complaints about Y, we're doing great I guess.
It's not a weird phrase to some, just as many folks have used terms like load-bearing for a long time. People are defending it because it reads fine to them, just as some are attacking it because it's not their preferred language, it causes them confusion, or they're just triggered and seething.
LLMs have made people so sensitive to language that I fear we're going to throw the baby out with the bath water. The models obviously need work, but they're also a great opportunity to expand our own vocabulary and grammar. It would be a shame if we deny some of the finer points of language in favor of Grug-speak to appease the lowest common denominator.
I think you're defending the wrong thing here. Claude isn't a English lit major writing a treatise on post-modernist allegories. In this context, it's primarily being used to churn out source code files, which are literal instructions for a computer to follow.
People aren't objecting to the use of obscure phrases, or flowery English phrases in itself. The issue is where Claude uses it out of place, or in the wrong context, or just plain overuses it.
It would be the equivalent of a young child learning the phrase "Venn diagram" - then using that identical phrase in every single subsequent interaction with others. Cute at first...but very grating after the n-th time.
You used the phrase "baby with the bath water. What if you started using that same phrase in every single HN post you made after this? People would notice very soon.
That's how it is with "load-bearing", or "plainly".
The other issue is where Claude takes a metaphor, and try to contort it to fit all sorts of absurd situations. What if I said "baby with the bath water" could also be used in place of "load-bearing". So every time you imagine Claude saying "load bearing", replace it with "baby with the bath water".
Nothing at all. You'll know when you've outgrown it.
> what the general workflow is now that people are converging to?
Graph-based workflows where agents pick up work as it becomes available, structured output, while you manage the work queue and outcomes. Maybe? IDK really, it's all moving quite fast.
Well, presumably AI lowers the bar for entry so more people (and very specifically people with revolutionary ideas, but without corresponding implementation skills) could get in on the action.
How many people with revolutionary ideas actually worth anything have genuinely failed to find someone to help them build it?
I think that if they're unable to sell their idea well enough to find a co-founder odds are the idea would die on the vine whether or not they're able to implement it.
https://chatgpt.com/ is a good starting point. Enable voice control and ask the robot to draw a pelican riding a bicycle. Much wow, very revolutionary. More to come.
The site looks nice, but I don't see an API option which makes it a non-starter for me. Having seen similar sites come and go over the years, I must assume that at some point my curated data will disappear. Or am I missing something?
No doubt the average person isn't going to be looking to integrate with your system via API, so maybe you're fine with it. Anyway, just some feedback from the fringe I suppose. Good luck with your project!
I've experimented quite a bit with giving agents python vs sed + awk. They make mistakes with both, a lot. The only thing that has stood out is that agents reach for python too quickly if it's available, and that awk causes the least problems, while sed might take several attempts to get results, similar to python.
reply